Skip to content

[python] update anthropic llmobs tests for new cache ttl metrics #6480

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Yun-Kim wants to merge 4 commits into
base: main
Choose a base branch
from
Draft

[python] update anthropic llmobs tests for new cache ttl metrics #6480

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5c5ca69
Update anthropic tests only for python new cache metrics
Yun-Kim Mar 12, 2026
dd9afe6
Merge remote-tracking branch 'origin/main' into yunkim/llmobs-anthrop…
Yun-Kim Mar 12, 2026
a33f54b
Revert missing_feature for python
Yun-Kim Mar 12, 2026
f557ccf
Merge branch 'main' into yunkim/llmobs-anthropic-ttl-cache-metrics
Yun-Kim Mar 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 0 additions & 7 deletions manifests/python.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1081,15 +1081,8 @@ manifest:
tests/ffe/test_flag_eval_metrics.py: missing_feature
tests/integration_frameworks/llm/anthropic/test_anthropic_apm.py::TestAnthropicApmMessages: v3.16.0
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages: v3.16.0
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create: missing_feature # ephemeral cache TTL metrics not yet released
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create_content_block: missing_feature # ephemeral cache TTL metrics not yet released
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create_error: bug (MLOB-1234)
? tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create_multiple_system_prompts
: missing_feature # ephemeral cache TTL metrics not yet released
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create_redact_image_input: missing_feature # ephemeral cache TTL metrics not yet released
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create_stream_method: missing_feature # ephemeral cache TTL metrics not yet released
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create_tool_result: bug (MLOB-1234)
tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py::TestAnthropicLlmObsMessages::test_create_with_tools: missing_feature # ephemeral cache TTL metrics not yet released
tests/integration_frameworks/llm/google_genai/test_google_genai_apm.py::TestGoogleGenAiEmbedContent: v3.11.0
tests/integration_frameworks/llm/google_genai/test_google_genai_apm.py::TestGoogleGenAiGenerateContent: v3.11.0
tests/integration_frameworks/llm/google_genai/test_google_genai_llmobs.py::TestGoogleGenAiEmbedContent: v3.13.0
Expand Down
15 changes: 15 additions & 0 deletions tests/integration_frameworks/llm/anthropic/test_anthropic_llmobs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,8 @@ def test_create(self, test_agent: TestAgentAPI, test_client: FrameworkTestClient
"total_tokens": mock.ANY,
"cache_read_input_tokens": mock.ANY,
"cache_write_input_tokens": mock.ANY,
"ephemeral_1h_input_tokens": mock.ANY,
"ephemeral_5m_input_tokens": mock.ANY,
},
)

Expand Down Expand Up @@ -124,6 +126,8 @@ def test_create_stream_method(self, test_agent: TestAgentAPI, test_client: Frame
"total_tokens": mock.ANY,
"cache_read_input_tokens": mock.ANY,
"cache_write_input_tokens": mock.ANY,
"ephemeral_1h_input_tokens": mock.ANY,
"ephemeral_5m_input_tokens": mock.ANY,
},
)

Expand Down Expand Up @@ -181,6 +185,8 @@ def test_create_content_block(self, test_agent: TestAgentAPI, test_client: Frame
"total_tokens": mock.ANY,
"cache_read_input_tokens": mock.ANY,
"cache_write_input_tokens": mock.ANY,
"ephemeral_1h_input_tokens": mock.ANY,
"ephemeral_5m_input_tokens": mock.ANY,
},
)

Expand Down Expand Up @@ -318,6 +324,8 @@ def test_create_multiple_system_prompts(
"total_tokens": mock.ANY,
"cache_read_input_tokens": mock.ANY,
"cache_write_input_tokens": mock.ANY,
"ephemeral_1h_input_tokens": mock.ANY,
"ephemeral_5m_input_tokens": mock.ANY,
},
)

Expand Down Expand Up @@ -384,6 +392,8 @@ def test_create_with_tools(self, test_agent: TestAgentAPI, test_client: Framewor
"total_tokens": mock.ANY,
"cache_read_input_tokens": mock.ANY,
"cache_write_input_tokens": mock.ANY,
"ephemeral_1h_input_tokens": mock.ANY,
"ephemeral_5m_input_tokens": mock.ANY,
},
)

Expand Down Expand Up @@ -501,6 +511,8 @@ def test_create_tool_result(self, test_agent: TestAgentAPI, test_client: Framewo
"total_tokens": mock.ANY,
"cache_read_input_tokens": mock.ANY,
"cache_write_input_tokens": mock.ANY,
"ephemeral_1h_input_tokens": mock.ANY,
"ephemeral_5m_input_tokens": mock.ANY,
},
)

Expand Down Expand Up @@ -574,6 +586,8 @@ def test_create_redact_image_input(
"total_tokens": mock.ANY,
"cache_read_input_tokens": mock.ANY,
"cache_write_input_tokens": mock.ANY,
"ephemeral_1h_input_tokens": mock.ANY,
"ephemeral_5m_input_tokens": mock.ANY,
},
)

Expand Down Expand Up @@ -630,4 +644,5 @@ def test_create_prompt_caching(
write_span_event, read_span_event = span_events

assert write_span_event["metrics"]["cache_write_input_tokens"] == 6163
assert write_span_event["metrics"]["ephemeral_5m_input_tokens"] == 6163
assert read_span_event["metrics"]["cache_read_input_tokens"] == 6163
Loading